Back to skill

Security audit

Training Exam Mgmt

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed exam-management prompt skill with no executable code, but users should handle candidate records, scores, and certificates under their own privacy and authorization controls.

Install only if you are comfortable using a Chinese-language exam-management prompt. Do not provide real candidate rosters, scores, exam content, or certificate data unless your organization authorizes that use and you have appropriate privacy, retention, approval, and audit procedures outside the skill.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill includes certificate generation and issuance as a supported workflow but does not define authorization checks, approval requirements, or fraud-prevention controls. Unauthorized or incorrect certificate issuance can falsely attest competence, damage organizational trust, and create downstream compliance, hiring, or safety risks depending on the certification's purpose.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly processes sensitive exam artifacts and candidate data, including candidate lists, detailed results, and certificate eligibility, but provides no privacy, access-control, retention, or handling guidance. In an exam-management context, this omission can lead to unauthorized disclosure of personal data, scores, and assessment content, as well as noncompliant processing of educational records.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The display name and description are written only in Chinese, with no indication that users can choose another language or locale. This creates a natural-language policy concern because the skill metadata appears to require a specific language experience without documented opt-in or justification.

Content

No source excerpt is available for this finding.